Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for product managers

Feature Request Prioritization Agent

A ranked, evidence-based backlog ready for planning

Feature Request Prioritization Agent: what goes in, what the agent does and what you get

What it does

Requests arrive daily from sales, support and customers, and backlog priority often follows the loudest customer. This agent gathers requests, merges duplicates and links each to the customers and revenue behind it. Two requests that sound different but solve the same problem are proposed for merging. It applies the team's scoring method, such as reach, impact, confidence and effort, using real data where possible. When a score depends on a guess like effort, it asks the engineering lead for an estimate. It checks the ranked list for sense: if one big customer pushes a request to the top on a single factor, it flags it for discussion. The product manager approves the ranked list.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueApprovedNo 1 STARTS WHEN Planning cycle approaches 2 USES A TOOL Collect requests from sales, support and feedbacktools 3 DOES Merge duplicates and link customers and revenue 4 USES A TOOL Request effort estimates for unscored items 5 DOES Score and rank requests 6 CHECKS THE RESULT Is any top-10 item driven by a single customer orfactor? If not: flag for discussion and show the score withoutthat factor. Back to step 5. 7 YOU APPROVE Product manager approves the ranked list 8 RESULT Ranked backlog in the planning tool
Read the steps as a list
  1. Planning cycle approaches
  2. Collect requests from sales, support and feedback tools
  3. Merge duplicates and link customers and revenue
  4. Request effort estimates for unscored items
  5. Score and rank requests
  6. Is any top-10 item driven by a single customer or factor?If not: flag for discussion and show the score without that factor. Back to step 5.
  7. Product manager approves the ranked listThe agent waits here for your OK.
  8. Ranked backlog in the planning tool

How it decides

It scores requests with the team's formula using linked evidence and flags any top item driven by one factor or one customer.

  • Duplicates merged when they solve the same user problem
  • Confidence lowered when evidence is one customer
  • Missing effort estimates block a final score

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Scoring formula and weights
  • Sources of requests
  • Planning cadence
  • Single-customer threshold

What keeps you in control

It always asks you first

  • Updating priorities in the planning tool
  • Telling customers about timing

Hard limits

  • Never promises delivery dates
  • Does not edit roadmap commitments

It stops when

  • Done: ranked list approved
  • Stop: scoring method not agreed

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensFrom 412 requests the agent merged 96 duplicates. An SSO request jumped to first place because one 900,000 dollar customer asked for it. The sense check flagged it: without that customer it ranked 14th. The agent drafted both views for discussion. Engineering estimated 3 weeks of effort. The product manager kept it at 6th.

More agents for product managers